Dorin Comaniciu
Princeton University
27 Papers
188 Citations
Dorin Comaniciu is an academic researcher from Princeton University. The author has contributed to research in topics: Computer science & Aortic valve. The author has an hindex of 8, co-authored 27 publications. Previous affiliations of Dorin Comaniciu include Vancouver General Hospital & Siemens.
Chat about Author
Papers
Combo loss: Handling input and output imbalance in multi-organ segmentation
Saeid Asgari Taghanaki,Saeid Asgari Taghanaki,Yefeng Zheng,S. Kevin Zhou,Bogdan Georgescu,Puneet Sharma,Daguang Xu,Dorin Comaniciu,Ghassan Hamarneh +8 more
TL;DR: In this article, a curriculum learning based loss function is proposed to handle the imbalance problem in both the input and output of a learning model for multi-organ segmentation, where the Dice similarity coefficient is leveraged to deter model parameters from being held at bad local minima and at the same time gradually learn better model parameters by penalizing for false positives/negatives using a cross entropy term.
335
•Proceedings Article
Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation
Saeid Asgari Taghanaki,Yefeng Zheng,S. Kevin Zhou,Bogdan Georgescu,Puneet Sharma,Daguang Xu,Dorin Comaniciu,Ghassan Hamarneh +7 more
- 08 May 2018
TL;DR: A new curriculum learning based loss function that leverages Dice similarity coefficient to deter model parameters from being held at bad local minima and at the same time gradually learn better model parameters by penalizing for false positives/negatives using a cross entropy term is introduced.
212
Automated quantification of CT patterns associated with COVID-19 from chest CT
Shikha Chaganti,Philippe Grenier,Abishek Balachandran,Guillaume Chabin,Stuart L. Cohen,Thomas Flohr,Bogdan Georgescu,Sasa Grbic,Siqi Liu,François Mellot,Nicolas Murray,Savvas Nicolaou,William Parker,Thomas J. Re,Pina C. Sanelli,Alexander W. Sauter,Zhoubing Xu,Youngjin Yoo,Valentin Ziebandt,Dorin Comaniciu +19 more
- 29 Jul 2020
TL;DR: A new method segments regions of CT abnormalities associated with COVID-19 and computes (PO, PHO), as well as (LSS, LHOS) severity scores, based on deep learning and deep reinforcement learning.
159
Patent
System and method for tracking a global shape of an object in motion
Xiang Sean Zhou,Dorin Comaniciu,Bogdan Georgescu,Sriram Krishnan +3 more
- 08 Mar 2004
TL;DR: In this paper, a system and method for tracking a global shape of an object in motion is disclosed, where one or more control points along an initial contour of the global shape are defined.
77
No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting With Adversarial Attacks
Siqi Liu,Arnaud Arindra Adiyoso Setio,Florin C. Ghesu,Eli Gibson,Sasa Grbic,Bogdan Georgescu,Dorin Comaniciu +6 more
TL;DR: In this paper, the authors proposed to add adversarial synthetic nodules and adversarial attack samples to the training data to improve the generalization and the robustness of the lung nodule detection systems.
52